Detection Of Abnormalities Research Articles

Detecting interest flooding attacks in NDN: A probability-based event-driven approach

The foundational concepts of the Internet were developed in the 1960s and 1970s with the goal of interconnecting hosts using the TCP/IP architecture. While this architecture has significantly impacted communication and commerce, it struggles to accommodate the Internet’s vast user base and diverse applications. Named Data Network (NDN), a next-generation Internet architecture is designed to overcome the current TCP/IP based Internet architecture’s limitations. NDN’s basic operations make it resilient against several traditional DoS/DDoS attacks. However, NDN remains vulnerable to Interest Flooding Attack (IFA), a class of DoS attacks that can exhaust the routers’ as well as the producers’ resources to disrupt network functionality. To detect these attacks, researchers came up with a few approaches. However, existing detection techniques focus on specific IFA variants but struggle to detect other variants. To address this challenge, in this paper, we propose a statistical abnormality detection scheme to identify all variants of IFA. Additionally, we generate a comprehensive NDN traffic dataset through our experiments and use it to evaluate the performance of the detection scheme. The experimental results show that our scheme can detect all variants of IFA with high accuracy. Towards the end, we also present a sensitivity analysis study that shows the impact of varying a few parameters on the detection performance of the proposed scheme.

ABNet: AI-Empowered Abnormal Action Recognition Method for Laboratory Mouse Behavior.

The automatic recognition and quantitative analysis of abnormal behavior in mice play a crucial role in behavioral observation experiments in neuroscience, pharmacology, and toxicology. Due to the challenging definition of abnormal behavior and difficulty in collecting training samples, directly applying behavior recognition methods to identify abnormal behavior is often infeasible. This paper proposes ABNet, an AI-empowered abnormal action recognition approach for mice. ABNet utilizes an enhanced Spatio-Temporal Graph Convolutional Network (ST-GCN) as an encoder; ST-GCN combines graph convolution and temporal convolution to efficiently capture and analyze spatio-temporal dynamic features in graph-structured data, making it suitable for complex tasks such as action recognition and traffic prediction. ABNet trains the encoding network with normal behavior samples, then employs unsupervised clustering to identify abnormal behavior in mice. Compared to the original ST-GCN network, the method significantly enhances the capabilities of feature extraction and encoding. We conduct comprehensive experiments on the Kinetics-Skeleton dataset and the mouse behavior dataset to evaluate and validate the performance of ABNet in behavior recognition and abnormal motion detection. In the behavior recognition experiments conducted on the Kinetics-Skeleton dataset, ABNet achieves an accuracy of 32.7% for the top one and 55.2% for the top five. Moreover, in the abnormal behavior analysis experiments conducted on the mouse behavior dataset, ABNet achieves an average accuracy of 83.1%.

Deep Learning-Based Blood Abnormalities Detection as a Tool for VEXAS Syndrome Screening.

VEXAS is a syndrome described in 2020, caused by mutations of the UBA1 gene, and displaying a large pleomorphic array of clinical and hematological features. Nevertheless, these criteria lack significance to discriminate VEXAS from other inflammatory conditions at the screening step. This work hence first focused on singling out dysplastic features indicative of the syndrome among peripheral blood (PB) polymorphonuclears (PMN). A deep learning algorithm is then proposed for automatic detection of these features. A multicentric dataset, comprising 9514 annotated PMN images was gathered, including UBA1 mutated VEXAS (n = 25), UBA1 wildtype myelodysplastic (n = 14), and UBA1 wildtype cytopenic patients (n = 25). Statistical analysis on a subset of patients was performed to screen for significant abnormalities. Detection of these features on PB was then automated with a convolutional neural network (CNN) for multilabel classification. Significant differences were observed in the proportions of PMNs with pseudo-Pelger, nuclear spikes, vacuoles, and hypogranularity between patients with VEXAS and both cytopenic and myelodysplastic controls. Automatic detection of these abnormalities yielded AUCs in the range [0.85-0.97] and a F1-score of 0.70 on the test set. A VEXAS screening score was proposed, leveraging the model outputs and predicting the UBA1 mutational status with 0.82 sensitivity and 0.71 specificity on the test patients. This study suggests that computer-assisted analysis of PB smears, focusing on suspected VEXAS cases, can provide valuable insights for determining which patients should undergo molecular testing. The presented deep learning approach can help hematologists direct their suspicions before initiating further analyses.

Abnormal behavior detection in industrial control systems based on CNN

With the widespread application of Internet of Things technology in industrial control systems, abnormal behavior detection has become a key task to ensure the safety and stable operation of the system. We propose a multi-branch convolutional fusion neural network method to improve the accuracy and efficiency of abnormal behavior detection in Internet of Things industrial control systems. This method achieves efficient detection of abnormal behavior in video data by combining ResNet152 for spatial feature extraction and GRU for temporal feature extraction. Unlike traditional methods, this method adopts a multi-branch structure, which can simultaneously capture multi-scale feature information, significantly enhancing the richness of feature expression and the accuracy of detection. Experimental results show that on the UCF-Crime dataset, the accuracy of this method reaches 85.76%, which is significantly better than that of traditional methods. In addition, on the larger UCF-101 dataset, the accuracy of this method reaches 92.21%, further verifying its excellent generalization performance. Compared with the C3D network, this method improves the accuracy by nearly 6% while maintaining a high processing speed. These results show that the proposed method has great potential in practical applications.

Multi-view attributed graph clustering based on graph diffusion convolution with adaptive fusion

Graph clustering is one of the popular techniques in data mining, which is widely used in social network analysis, recommendation system and anomaly detection. The existing methods based on multi-view attributed graph ignore the difference of different views and the consistency between views. To this end, this paper proposes a novel method for multi-view attributed graph clustering based on graph diffusion convolution with adaptive fusion. Specifically, a graph diffusion convolution is firstly employed to propagate features of the adjacency and attribute matrices on each view. A linear encoder–decoder is then used to learn the graph embedding representation of each view. Meanwhile, the consistency learning module is applied to capture the geometric relationship consistency of different views for finding a consistent embedding space during the embedding representation learning. To measure the importance of different views, the attention mechanism is subsequently utilized to adaptively learn the weights of different views to fuse multiple views of data for the final clustering. Finally, the graph representation learning and clustering tasks are jointly optimized to obtain a clustering friendly graph representation. Experiments conducted on two public datasets and three real futures datasets from the Zhengzhou Commodity Exchange demonstrate the effectiveness of the proposed method in the task of graph clustering.

A CNN based model for heart disease detection

Cardiovascular diseases (CVDs) pose a formidable global health challenge, claiming millions of lives annually. Despite advancements in healthcare, heart disease remains a leading cause of mortality, especially in developing nations. Early detection of cardiac abnormalities through predictive models is crucial for effective intervention. This research leverages machine learning (ML) and artificial intelligence (AI), focusing on deep learning, to enhance diagnostic capabilities. Unlike previous studies, this work introduced caffeine as a potential risk factor often overlooked in datasets. The study utilized Magnetic Resonance Imaging (MRI) datasets from Enugu State University Teaching Hospital and Kaggle, comprising 90,500 samples, with specific attention to high caffeine intake cases. Data preprocessing involved resizing, normalization, color adjustments, and augmentation to optimize model training. A Convolutional Neural Network (CNN) architecture with four convolutional layers was employed for classification. The CNN model achieved a remarkable accuracy of 94% and low loss values, and demonstrated proficiency in categorizing heart MRI data. Ten-fold cross-validation reaffirmed the model's high success rate with an average accuracy of 94.13% and minimal loss function. Comparative analysis showcased the effectiveness of the developed CNN model, outperforming several existing models in heart disease classification.

SSRLM: A self-supervised representation learning method for identifying one ship with multi-MMSI codes

It is of great practical significance for maritime safety and shipping development to achieve “One Ship with One Maritime Mobile Service Identity (MMSI) Code” in accordance with regulations. However, the current “One Ship with Multiple MMSI Codes” violation identification method lacks practicability and generalization. Aiming at the these problems, this paper proposes a self-supervised representation learning model for the “One Ship with Multiple MMSI Codes” abnormal behavior recognition task, named SSRLM. Firstly, we construct a new dataset about “One Ship with Multiple MMSI Codes”, named HN_MulMI. Secondly, the SSRLM model learns the contextual interdependencies among different trajectory features in the HN_MulMI dataset through an unsupervised pre-training scheme, and extracts a dense vectorial representation of the ship’s motion trajectories. Finally, by using the unique characteristics of the “One Ship with Multiple MMSI Codes” trajectory sequence, the SSRLM model captures its feature dependencies through a fine-tuning scheme to accomplish the abnormal behavior detection task. Experimental results in the two scenarios of HN_MulMI test set demonstrate that the proposed model outperform the state-of-the-art models in recent years, the average precision, recall and F1-score rates is up to about 99.26% and 93.5%. Meanwhile, we also conducted comparative experiments on three public datasets to verify the generalization performance, achieving 90.31%, 93.2% and 95.14% results in the F1 score evaluation indicators, further confirming the good recognition performance of the SSLLM model. Finally, our model has been applied to the actual scene and achieved good results.

Electrocardiographic abnormalities and associated factors among HIV-infected adults on antiretroviral therapy.

Individuals living with HIV are at increased risk of developing cardiovascular diseases. This heightened vulnerability is influenced by various factors, including the direct impact of HIV infection, the side effects of HIV medications, and a higher presence of traditional cardiovascular risk factors. Detecting and managing cardiovascular diseases early in HIV-infected individuals is crucial for their overall health and well-being. Electrocardiography, a simple and non-invasive test, can provide valuable information in this regard. However, there is currently no published data on the prevalence of electrocardiographic abnormalities and the associated factors among HIV-infected adults in Ethiopia. This study was aimed at assessing the prevalence of ECG abnormalities and associated factors among HIV-infected adults on antiretroviral therapy. A hospital-based comparative cross-sectional study was conducted at Mettu Karl Specialized Hospital (MKSH), southwest Ethiopia, among 96 HIV-infected patients and 96 HIV-negative control groups. A systematic random sampling technique was used to select HIV-infected respondents, and HIV-negative respondents were purposively recruited from caregivers. A face-to-face interview with a semi-structured and pretested questionnaire was conducted to collect the socio-demographic and behavioral characteristics of the study participants. Electrocardiography was done for all study participants using a 12-lead electrocardiograph, interpreted by a cardiologist, and classified according to the Minnesota Code classification system. The data were entered into Epi-Data version 4.6 and exported to SPSS version 25 for analysis. Finally, descriptive statistics, chi-square, independent t-test, bivariable, and multivariable logistic regression analyses were done at a 5% significance level. The study found that 49% of HIV-infected and 19.8% of HIV-negative participants had at least one ECG abnormality. The proportion of coded ST-segment abnormalities, T-wave abnormalities, longer QT interval, and sinus tachycardia was significantly higher in HIV-infected respondents than in HIV-negatives. Being a smoker [AOR = 3.7, 95%CI: 1.03-13.6], being on Protease inhibitors [AOR = 3.6, 95%CI: 1.02-13.1] and having CD4 less than 350 cells/mm3 [AOR = 3.2, 95%CI: 1.22-8.49] were significantly associated with ECG abnormalities among HIV-infected respondents. Compared to HIV-negative participants, HIV-infected patients had a significantly higher prevalence of ECG abnormalities. Screening for ECG abnormalities is needed for the early detection of cardiac abnormalities and the reduction of future complications.

Detection of multiple abnormalities of breast cancer in mammograms using a deep dilated fully convolutional neural network

Breast cancer is one of the serious health issues which are quite frequent among women and the mortality rate due to it can be reduced if detected and diagnosed at the early stage. In this paper, a new generalized deep learning architecture, deep dilated fully convolutional neural network (DDFCNN), is designed to detect multiple abnormalities like mass, microcalcification, and architectural distortion in mammograms. The proposed DDFCNN architecture consists of a feature and a dilation module. In feature module, convolutional kernels of various sizes are used to capture information at different scales. Since there is no loss of resolution in the output of the dilation module, it renders more details which helps in localizing the anomaly properly. Several experiments are conducted on a widely used databases — DDSM and mini-MIAS where an accuracy of 95.33%, 91.42%, and 92.67% is measured for detection of mass, microcalcification, and architectural distortion, respectively with a FPs/I of 0.43, 0.50, and 0.46 for DDSM and similar assessment for mini-MIAS database are 96.56%, 89.63%, and 95.07% with a FPs/I of 0.29, 0.51, and 0.31. Moreover, the overall performance in detection of all the abnormalities in combination is 93.14% with 0.46 as FPs/I for DDSM whereas for mini-MIAS is 93.75% with 0.37 as FPs/I. The performance is further compared with the state-of-the-other methods where the proposed approach takes an edge.

Muscular dystrophy patients show low exercise‐induced blood flow in muscles with normal strength

AbstractObjectiveNeuromuscular evaluation increasingly employs muscle ultrasonography to determine muscle thickness, mean grayscale echointensity, and visual semiquantitative echotexture attenuation. However, these measures provide low sensitivity for detection of mild muscle abnormality. Exercise‐induced intramuscular blood flow is a physiologic phenomenon, which may be impaired in mildly affected muscles, particularly in dystrophinopathies, and may indicate functional muscle ischemia. We aimed to determine if muscle blood flow is reduced in patients with neuromuscular disorders and preserved muscle strength, and if it correlates with echointensity and digital echotexture measurements.MethodsPeak exercise‐induced blood flow, echointensity, and echotexture were quantified in the elbow flexor muscles of 15 adult patients with Becker muscular dystrophy (BMD) and 13 patients with other muscular dystrophies (OMD). These were compared to 17 patients with Charcot–Marie–Tooth type 1 (CMT1) neuropathy and 21 healthy adults from a previous study.ResultsMuscle blood flow was reduced in all patient groups compared to controls, most prominently in BMD patients (p < 0.0001). Echointensity was similarly increased in all patient groups (p < 0.05), while echotexture was reduced only in muscular dystrophy patients (p ≤ 0.002). In BMD, blood flow correlated with echotexture (Pearson r = 0.6098, p = 0.0158) and strength (Spearman r = 0.5471; p = 0.0370). In patients with normal muscle strength, reduced muscle blood flow was evident in all patient groups (p < 0.001), echotexture was reduced in BMD and OMD (p < 0.01), and echointensity was increased in CMT (p < 0.05).InterpretationMuscle blood flow is a sensitive measure to detect abnormality, even in muscles with normal strength. Increased echointensity may indicate a neurogenic disorder when strength is preserved, while low echotexture suggests a dystrophic disease.

The protean presentations of XK disease (McLeod syndrome): a case series with new observations and updates on previously reported families.

XK disease is a very rare, multi-system disease, which can present with a wide spectrum of symptoms. This disorder can also be identified pre-symptomatically with the incidental detection of serological abnormalities when typing erythrocytes in peripheral blood, or on other routine laboratory testing. Increasing awareness of this disorder and improved access to genetic testing are resulting in increasing identification of affected patients and families. Here we provide updates to some previously-reported families and patients and provide additional clinical details. We also report four new cases with a variety of presentations, one of whom had a novel mutation.

The Use of Genomic Screening for the Detection of Chromosomal Abnormalities in the Domestic Horse: Five New Cases of 65,XXY Syndrome in the Pura Raza Español Breed.

Sex chromosomal abnormalities are a well-established cause of reproductive failure in domestic horses. Because of its difficult diagnosis, the Pura Raza Español breeding program established a routine screening for chromosomal abnormalities in all the horses prior to enrolling in the studbook. This genomic procedure combines an initial assessment based on the results from Short Tandem Repeat (STR) parentage testing followed by a Single-Nucleotide Polymorphism (SNP) based copy number aberration (CNA) confirmative analysis in positive cases. Using this methodology, we identified five new individuals carrying a 65,XXY chromosomal number aberration (CNA) among 27,330 foals enrolled over the past two reproductive seasons. The animals were initially flagged as CNA candidates due to abnormal results in STR testing. Subsequent analysis genotyping using an STR sex-linked dedicated panel and a medium-density SNP array in ECAX and ECAY confirmed the diagnosis as 65,XXY carriers. Four cases (upon sample availability) underwent further analysis using in situ fluorescent hybridization with ECAX and ECAY probes, showing identical results. Phenotypic analysis revealed abnormal gonad development in one of the cases, showing that the remaining four had a normal reproductive morphology. To our knowledge, this represents the largest number of horses exhibiting the equine form of Klinefelter syndrome (65,XXY) reported to date. Our study highlights the importance of genomic screening in the accurate detection of chromosomal abnormalities in horses.

Local–global normality learning and discrepancy normalizing flow for unsupervised image anomaly detection

The unsupervised detection and localization of image anomalies hold significant importance across various domains, particularly in industrial quality inspection. Despite its widespread utilization, this task remains inherently challenging due to its reliance solely on defect-free normal knowledge. This paper presents the local–global normality learning and discrepancy normalizing flow, a new state-of-the-art model for unsupervised image anomaly detection and localization. In contrast to existing methods, It adopts a two-stream approach that considers both local and global semantics, ensuring stable detection of abnormalities. The framework comprises two key components: the dual-branch Transformer and the discrepancy normalizing flow, facilitating reconstruction and discrimination. The proposed framework leverages pre-trained convolutional neural networks to extract multi-scale feature embeddings, followed by a novel dual-branch transformer that achieves feature reconstruction from local and global perspectives. The local reconstruction employs self-attention, while the global reconstruction incorporates global prototype tokens and semantic query tokens by the aggregation-cross attention mechanism. Moreover, discrepancy normalizing flow is developed to estimate the likelihood of anomalies based on the discrepancy between pre-trained features and local/global reconstruction results. Extensive validation on established public benchmarks confirms that our method achieves state-of-the-art performance with the proposed local–global reconstruction and discrimination dual-stream framework.

Exponential Pixelating Integral transform with dual fractal features for enhanced chest X-ray abnormality detection

The heightened prevalence of respiratory disorders, particularly exacerbated by a significant upswing in fatalities due to the novel coronavirus, underscores the critical need for early detection and timely intervention. This imperative is paramount, possessing the potential to profoundly impact and safeguard numerous lives. Medically, chest radiography stands out as an essential and economically viable medical imaging approach for diagnosing and assessing the severity of diverse Respiratory Disorders. However, their detection in Chest X-Rays is a cumbersome task even for well-trained radiologists owing to low contrast issues, overlapping of the tissue structures, subjective variability, and the presence of noise. To address these issues, a novel analytical model termed Exponential Pixelating Integral is introduced for the automatic detection of infections in Chest X-Rays in this work. Initially, the presented Exponential Pixelating Integral enhances the pixel intensities to overcome the low-contrast issues that are then polar-transformed followed by their representation using the locally invariant Mandelbrot and Julia fractal geometries for effective distinction of structural features. The collated features labeled Exponential Pixelating Integral with dually characterized fractal features are then classified by the non-parametric multivariate adaptive regression splines to establish an ensemble model between each pair of classes for effective diagnosis of diverse diseases. Rigorous analysis of the proposed classification framework on large medical benchmarked datasets showcases its superiority over its peers by registering a higher classification accuracy and F1 scores ranging from 98.46 to 99.45 % and 96.53–98.10 % respectively, making it a precise and interpretable automated system for diagnosing respiratory disorders.

Phonocardiogram Signal Analysis Based Premature Cardiac Influence Detection using Resnet50 CNN for Public Health Protection

Phonocardiogram (PCG) signal analysis plays a crucial role in the early detection of cardiac abnormalities, which is essential for public health protection. The premature disease prediction is tedious because the feature analysis takes place dimensionality problems which leads poor accuracy. The prevailing ensemble learning models’ methods doesn’t concentrate disease margin facts and properties during classification produce higher false rate because for adjusting feature margins gets lower accuracy. To resolve this problem, we propose a efficient Fuzzy c-means feature modality based Resnet50-RNN to detect premature cardiac influence detection for improving public health. The research proposes a method for premature cardiac influence detection using a ResNet50 Convolutional Neural Network (CNN) model for early prediction of heart disease. To address the issue of imbalanced data, Synthetic Minority Oversampling Technique (SMOTE) is employed for preprocessing. The Cardiac Disease Influence Rate (CDIR) is then used to identify the maximum deficiency-affected feature margins. Fuzzy c-means is utilized to select the mutual features associated with the heart disease influence rate. The ResNet50 CNN model is employed for classification, enabling the prediction of disease margins by risk category. The proposed system effectively identifies the disease based on the disease-affected scaling margin, leading to early disease impact prediction with higher accuracy, specificity, F1-measure, and lower false rates compared to other existing systems. The implementation also demonstrates reduced time complexity.

Role of ultrasound and magnetic resonance neurography in the detection of median nerve abnormalities in carpal tunnel syndrome

BackgroundThe most prevalent cause of peripheral nerve entrapment is carpal tunnel syndrome, which is characterized by compression of the median nerve at the wrist as a result of nearby or localized microvascular interference as well as structural alterations to the median nerve or adjacent tissues. However, no special information regarding the median nerve or its surroundings is provided by clinical examination or electrophysiological testing. The purpose of this study is to evaluate the effectiveness of magnetic resonance neurography (MRN) and ultrasound in identifying changes and abnormalities of the median nerve in carpal tunnel syndrome.MethodsThe twenty-five patients in this study ranged in age from 27 to 63 years old, with a mean age of 47. There were 18 female patients and seven male patients. All patients were sent to the radiology department from the orthopedics, neurology, outpatient clinic, and neurology department, at Ain Shams Hospital, Faculty of Medicine, Ain Shams University. All of the patients had clinically manifested pain along the median nerve distribution, each of the sixteen patients had hand paresthesia, and four had thenar muscle atrophy.ResultsIn the current study, Ultrasound exhibits low negative predictive value of 67% and specificity of 67%, but high positive predictive value of 95%, sensitivity of 95%, and overall accuracy of 92%. On the other hand, (MRN) exhibits a low negative predictive value of 60% and a high specificity of 75% in the diagnosis of nerve entrapment, but it also displays a high positive predictive value of 95%, sensitivity of 90%, and overall accuracy of 88%. Regarding the assessment of the recurrence cause and post-surgical evaluation is more reliable by Magnetic Resonance Neurography examination.ConclusionsMagnetic resonance neurography and high-resolution ultrasonography can be utilized to diagnose patients with median nerve entrapment and patients who cannot be diagnosed electrophysiologically.MRN is a more accurate method for detecting the exact location of nerve entrapment and evaluating nerve recovery after surgical intervention than nerve conduction studies and electromyography. Additionally, MRN can be used to identify causes that were not previously recognized based on physical examination and electrophysiological tests.

Electricity behaviors anomaly detection based on multi-feature fusion and contrastive learning

Abnormal electricity usage detection is the process of discovering and diagnosing abnormal electricity usage behavior by monitoring and analyzing the electricity usage in the power system. How to improve the accuracy of anomaly detection is a popular research topic. Most studies use neural networks for anomaly detection, but ignore the effect of missing electricity data on anomaly detection performance. Missing value completion is an important method to improve the quality of electricity data and to optimize the anomaly detection performance. Moreover, most studies have ignored the potential correlation relationship between spatial features by modeling the temporal features of electricity data. Therefore, this paper proposes an electricity anomaly detection model based on multi-feature fusion and contrastive learning. The model integrates the temporal and spatial features to jointly accomplish electricity anomaly detection. In terms of temporal feature representation learning, an improved bi-directional LSTM is designed to achieve the missing value completion of electricity data, and combined with CNN to capture the electricity consumption behavior patterns in the temporal data. In terms of spatial feature representation learning, GCN and Transformer are used to fully explore the complex correlation relationships among data. In addition, in order to improve the performance of anomaly detection, this paper also designs a gated fusion module and combines the idea of contrastive learning to strengthen the representation ability of electricity data. Finally, we demonstrate through experiments that the method proposed in this paper can effectively improve the performance of electricity behavior anomaly detection.

A Trusted Supervision Paradigm for Autonomous Driving Based on Multimodal Data Authentication

At the current stage of autonomous driving, monitoring the behavior of safety stewards (drivers) is crucial to establishing liability in the event of an accident. However, there is currently no method for the quantitative assessment of safety steward behavior that is trusted by multiple stakeholders. In recent years, deep-learning-based methods can automatically detect abnormal behaviors with surveillance video, and blockchain as a decentralized and tamper-resistant distributed ledger technology is very suitable as a tool for providing evidence when determining liability. In this paper, a trusted supervision paradigm for autonomous driving (TSPAD) based on multimodal data authentication is proposed. Specifically, this paradigm consists of a deep learning model for driving abnormal behavior detection based on key frames adaptive selection and a blockchain system for multimodal data on-chaining and certificate storage. First, the deep-learning-based detection model enables the quantification of abnormal driving behavior and the selection of key frames. Second, the key frame selection and image compression coding balance the trade-off between the amount of information and efficiency in multiparty data sharing. Third, the blockchain-based data encryption sharing strategy ensures supervision and mutual trust among the regulatory authority, the logistic platform, and the enterprise in the driving process.

Optimized Tiny Machine Learning and Explainable AI for Trustable and Energy-Efficient Fog-Enabled Healthcare Decision Support System

The Internet of things (IoT)-based healthcare decision support system plays a crucial role in modern medicine, especially with the rise in chronic illnesses and an aging population necessitating continuous remote health monitoring. Current healthcare decision support systems struggle to deliver timely and accurate decisions with minimal latency due to limited real-time healthcare data and inefficient computational resources. There is a critical need for an optimized, energy-efficient machine learning model that reliably supports remote health monitoring within IoT and fog computing environments. Our study proposes an Optimized Tiny Machine Learning (TinyML) and Explainable AI (XAI) binary classification model for a trustable and energy-efficient healthcare decision support system, leveraging fog computing to optimize performance. The fog-based approach improves response times and enhances bandwidth usage, addressing critical needs such as reduced latency, higher bandwidth utilization, and decreased packet loss. To further improve efficiency, we incorporate the innovative mLZW data compression technique, significantly enhancing data communication efficiency and reducing response time to critical health alerts. However, limited real-time healthcare data records challenge machine learning classification performance. By implementing a TinyML algorithm, our system demonstrates superior performance to other machine learning models. The proposed optimized TinyML model achieves an impressive F1 score of 0.93 for health abnormalities detection, emphasizing its robustness and effectiveness. This paper highlights the potential of TinyML and XAI in delivering robust, trustworthy, and energy-aware healthcare solutions, making significant contributions toward effective remote health monitoring and decision support in fog-enabled IoT networks.Graphical abstract

Classification of Prehospital Electrocardiograms Performed in Ambulances According to Severity Using a Deep Learning Neural Network

Prehospital electrocardiogram (PH-ECG) transmission is an important technology for reducing door-to-balloon time, but the decision to transmit often depends on the discretion of emergency medical technicians (EMTs). Additionally, studies based on real-world data remain insufficient. This study reports a machine learning-based method for classifying the severity of PH-ECG images and explores its feasibility. PH-ECG data were compiled from 120 patients between September 2017 and September 2020. The model we created from these data was the first classification model for PH-ECG images using data from a Japanese study population and showed a weighted F1-score of 0.85 and an Area Under the Curve (AUC) of 0.93. This result can be interpreted as having an excellent balance of sensitivity and specificity. The Cohen’s Kappa coefficient between AI’s inferences and the correct labels created by two cardiologists was 0.68 (p < 0.05), which is considered “substantial” according to the guidelines presented by Landis and Koch. In this study, although we were not able to remove noise caused by patient movement or electrode detachment, the results indicate that image-based abnormality detection from PH-ECGs is feasible and effective, particularly in regions like Japan where ECG data are often stored and transmitted as images. In addition, in our region, paramedics follow a multi-step process to decide whether to transmit an ECG, which takes time for the first screening. However, if the ECG is transmitted when either the paramedics or the deep learning model detects an abnormality, it is expected to reduce reading time and door-to-balloon time, as well as decrease false negatives.